Early prediction of outcome after severe traumatic brain injury

A simple and practical model

Sandro Rizoli, Ashley Petersen, Eileen Bulger, Raul Coimbra, Jeffrey D. Kerby, Joseph Minei, Laurie Morrison, Avery Nathens, Martin Schreiber, Airton Leonardo de Oliveira Manoel

    Research output: Contribution to journalArticle

    6 Citations (Scopus)

    Abstract

    Background: Traumatic brain injury (TBI) is a heterogeneous syndrome with a broad range of outcome. We developed a simple model for long-term outcome prognostication after severe TBI. Methods: Secondary data analysis of a large multicenter randomized trial. Patients were grouped according to 6-month extended Glasgow outcome scale (eGOS): poor-outcome (eGOS ≤ 4; severe disability or death) and acceptable outcome (eGOS > 4; no or moderate disability). A prediction decision tree was built using binary recursive partitioning to predict poor or acceptable 6-month outcome. Comparison to two previously published and validated models was made. Results: The decision tree included the predictors of head Abbreviated Injury Scale (AIS) severity, the Marshall computed tomography score, and pupillary reactivity. All patients with a head AIS severity of 5 were predicted to have a poor outcome. In patients with head AIS severity < 5, the model predicted an acceptable outcome for (1) those with Marshall score of 1, and (2) those with Marshall score above 1 but with reactive pupils at admission. The decision tree had a sensitivity of 72.3 % (95 % CI: 66.4-77.6 %) and specificity of 62.5 % (95 % CI: 54.9-69.6 %). The proportion correctly classified for the comparison models was similar to our model. Our model was more apt at correctly classifying those with poor outcome but more likely to misclassify those with acceptable outcome than the comparison models. Conclusion: Predicting long-term outcome early after TBI remains challenging and inexact. This model could be useful for research and quality improvement studies to provide an early assessment of injury severity, but is not sufficiently accurate to guide decision-making in the clinical setting.

    Original languageEnglish (US)
    Article number32
    JournalBMC Emergency Medicine
    Volume16
    Issue number1
    DOIs
    StatePublished - Aug 24 2016

    Fingerprint

    Abbreviated Injury Scale
    Glasgow Outcome Scale
    Decision Trees
    Craniocerebral Trauma
    Pupil
    Quality Improvement
    Multicenter Studies
    Tomography
    Wounds and Injuries
    Research
    carbosulfan
    Traumatic Brain Injury

    Keywords

    • Outcome measures
    • Prognostic models
    • Recovery
    • Traumatic brain injury

    ASJC Scopus subject areas

    • Emergency Medicine

    Cite this

    Rizoli, S., Petersen, A., Bulger, E., Coimbra, R., Kerby, J. D., Minei, J., ... de Oliveira Manoel, A. L. (2016). Early prediction of outcome after severe traumatic brain injury: A simple and practical model. BMC Emergency Medicine, 16(1), [32]. https://doi.org/10.1186/s12873-016-0098-x

    Early prediction of outcome after severe traumatic brain injury : A simple and practical model. / Rizoli, Sandro; Petersen, Ashley; Bulger, Eileen; Coimbra, Raul; Kerby, Jeffrey D.; Minei, Joseph; Morrison, Laurie; Nathens, Avery; Schreiber, Martin; de Oliveira Manoel, Airton Leonardo.

    In: BMC Emergency Medicine, Vol. 16, No. 1, 32, 24.08.2016.

    Research output: Contribution to journalArticle

    Rizoli, S, Petersen, A, Bulger, E, Coimbra, R, Kerby, JD, Minei, J, Morrison, L, Nathens, A, Schreiber, M & de Oliveira Manoel, AL 2016, 'Early prediction of outcome after severe traumatic brain injury: A simple and practical model', BMC Emergency Medicine, vol. 16, no. 1, 32. https://doi.org/10.1186/s12873-016-0098-x
    Rizoli, Sandro ; Petersen, Ashley ; Bulger, Eileen ; Coimbra, Raul ; Kerby, Jeffrey D. ; Minei, Joseph ; Morrison, Laurie ; Nathens, Avery ; Schreiber, Martin ; de Oliveira Manoel, Airton Leonardo. / Early prediction of outcome after severe traumatic brain injury : A simple and practical model. In: BMC Emergency Medicine. 2016 ; Vol. 16, No. 1.
    @article{df5d709c1a9b458eac9d7120254ca586,
    title = "Early prediction of outcome after severe traumatic brain injury: A simple and practical model",
    abstract = "Background: Traumatic brain injury (TBI) is a heterogeneous syndrome with a broad range of outcome. We developed a simple model for long-term outcome prognostication after severe TBI. Methods: Secondary data analysis of a large multicenter randomized trial. Patients were grouped according to 6-month extended Glasgow outcome scale (eGOS): poor-outcome (eGOS ≤ 4; severe disability or death) and acceptable outcome (eGOS > 4; no or moderate disability). A prediction decision tree was built using binary recursive partitioning to predict poor or acceptable 6-month outcome. Comparison to two previously published and validated models was made. Results: The decision tree included the predictors of head Abbreviated Injury Scale (AIS) severity, the Marshall computed tomography score, and pupillary reactivity. All patients with a head AIS severity of 5 were predicted to have a poor outcome. In patients with head AIS severity < 5, the model predicted an acceptable outcome for (1) those with Marshall score of 1, and (2) those with Marshall score above 1 but with reactive pupils at admission. The decision tree had a sensitivity of 72.3 {\%} (95 {\%} CI: 66.4-77.6 {\%}) and specificity of 62.5 {\%} (95 {\%} CI: 54.9-69.6 {\%}). The proportion correctly classified for the comparison models was similar to our model. Our model was more apt at correctly classifying those with poor outcome but more likely to misclassify those with acceptable outcome than the comparison models. Conclusion: Predicting long-term outcome early after TBI remains challenging and inexact. This model could be useful for research and quality improvement studies to provide an early assessment of injury severity, but is not sufficiently accurate to guide decision-making in the clinical setting.",
    keywords = "Outcome measures, Prognostic models, Recovery, Traumatic brain injury",
    author = "Sandro Rizoli and Ashley Petersen and Eileen Bulger and Raul Coimbra and Kerby, {Jeffrey D.} and Joseph Minei and Laurie Morrison and Avery Nathens and Martin Schreiber and {de Oliveira Manoel}, {Airton Leonardo}",
    year = "2016",
    month = "8",
    day = "24",
    doi = "10.1186/s12873-016-0098-x",
    language = "English (US)",
    volume = "16",
    journal = "BMC Emergency Medicine",
    issn = "1471-227X",
    publisher = "BioMed Central",
    number = "1",

    }

    TY - JOUR

    T1 - Early prediction of outcome after severe traumatic brain injury

    T2 - A simple and practical model

    AU - Rizoli, Sandro

    AU - Petersen, Ashley

    AU - Bulger, Eileen

    AU - Coimbra, Raul

    AU - Kerby, Jeffrey D.

    AU - Minei, Joseph

    AU - Morrison, Laurie

    AU - Nathens, Avery

    AU - Schreiber, Martin

    AU - de Oliveira Manoel, Airton Leonardo

    PY - 2016/8/24

    Y1 - 2016/8/24

    N2 - Background: Traumatic brain injury (TBI) is a heterogeneous syndrome with a broad range of outcome. We developed a simple model for long-term outcome prognostication after severe TBI. Methods: Secondary data analysis of a large multicenter randomized trial. Patients were grouped according to 6-month extended Glasgow outcome scale (eGOS): poor-outcome (eGOS ≤ 4; severe disability or death) and acceptable outcome (eGOS > 4; no or moderate disability). A prediction decision tree was built using binary recursive partitioning to predict poor or acceptable 6-month outcome. Comparison to two previously published and validated models was made. Results: The decision tree included the predictors of head Abbreviated Injury Scale (AIS) severity, the Marshall computed tomography score, and pupillary reactivity. All patients with a head AIS severity of 5 were predicted to have a poor outcome. In patients with head AIS severity < 5, the model predicted an acceptable outcome for (1) those with Marshall score of 1, and (2) those with Marshall score above 1 but with reactive pupils at admission. The decision tree had a sensitivity of 72.3 % (95 % CI: 66.4-77.6 %) and specificity of 62.5 % (95 % CI: 54.9-69.6 %). The proportion correctly classified for the comparison models was similar to our model. Our model was more apt at correctly classifying those with poor outcome but more likely to misclassify those with acceptable outcome than the comparison models. Conclusion: Predicting long-term outcome early after TBI remains challenging and inexact. This model could be useful for research and quality improvement studies to provide an early assessment of injury severity, but is not sufficiently accurate to guide decision-making in the clinical setting.

    AB - Background: Traumatic brain injury (TBI) is a heterogeneous syndrome with a broad range of outcome. We developed a simple model for long-term outcome prognostication after severe TBI. Methods: Secondary data analysis of a large multicenter randomized trial. Patients were grouped according to 6-month extended Glasgow outcome scale (eGOS): poor-outcome (eGOS ≤ 4; severe disability or death) and acceptable outcome (eGOS > 4; no or moderate disability). A prediction decision tree was built using binary recursive partitioning to predict poor or acceptable 6-month outcome. Comparison to two previously published and validated models was made. Results: The decision tree included the predictors of head Abbreviated Injury Scale (AIS) severity, the Marshall computed tomography score, and pupillary reactivity. All patients with a head AIS severity of 5 were predicted to have a poor outcome. In patients with head AIS severity < 5, the model predicted an acceptable outcome for (1) those with Marshall score of 1, and (2) those with Marshall score above 1 but with reactive pupils at admission. The decision tree had a sensitivity of 72.3 % (95 % CI: 66.4-77.6 %) and specificity of 62.5 % (95 % CI: 54.9-69.6 %). The proportion correctly classified for the comparison models was similar to our model. Our model was more apt at correctly classifying those with poor outcome but more likely to misclassify those with acceptable outcome than the comparison models. Conclusion: Predicting long-term outcome early after TBI remains challenging and inexact. This model could be useful for research and quality improvement studies to provide an early assessment of injury severity, but is not sufficiently accurate to guide decision-making in the clinical setting.

    KW - Outcome measures

    KW - Prognostic models

    KW - Recovery

    KW - Traumatic brain injury

    UR - http://www.scopus.com/inward/record.url?scp=84983340652&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84983340652&partnerID=8YFLogxK

    U2 - 10.1186/s12873-016-0098-x

    DO - 10.1186/s12873-016-0098-x

    M3 - Article

    VL - 16

    JO - BMC Emergency Medicine

    JF - BMC Emergency Medicine

    SN - 1471-227X

    IS - 1

    M1 - 32

    ER -